Developer · Local MCP server

Kafka Sentinel

Read-only Kafka observability MCP server: cluster health, consumer lag, and replay-readiness.

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.sanjay-amu/kafka-sentinel-mcp
Version
0.1.2
Status
Active
Category
developer
Transport
stdio (local process)
Package
PyPI
Published
2026-07-23
Updated
2026-07-23
Publisher
sanjay-amu (GitHub)
Listed under
Kafka MCP servers
Repository
github.com/sanjay-amu/kafka-sentinel-mcp
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
PyPIkafka-sentinel-mcp0.1.2stdioKAFKA_BOOTSTRAP (required), KAFKA_SECURITY_PROTOCOL, KAFKA_SASL_MECHANISM, KAFKA_SASL_USERNAME, KAFKA_SASL_PASSWORD (secret), KAFKA_SSL_CA_LOCATION

How to connect Kafka Sentinel

Kafka Sentinel runs locally from a Python package published to PyPI: kafka-sentinel-mcp version 0.1.2. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install — the usual command is uvx kafka-sentinel-mcp. It reads these environment variables: KAFKA_BOOTSTRAP (required), KAFKA_SECURITY_PROTOCOL, KAFKA_SASL_MECHANISM, KAFKA_SASL_USERNAME, KAFKA_SASL_PASSWORD (secret) and KAFKA_SSL_CA_LOCATION; set them in the client's configuration for this server.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "kafka-sentinel-mcp": {
      "command": "uvx",
      "args": [
        "kafka-sentinel-mcp"
      ],
      "env": {
        "KAFKA_BOOTSTRAP": "<value>",
        "KAFKA_SECURITY_PROTOCOL": "<value>",
        "KAFKA_SASL_MECHANISM": "<value>",
        "KAFKA_SASL_USERNAME": "<value>",
        "KAFKA_SASL_PASSWORD": "<secret>",
        "KAFKA_SSL_CA_LOCATION": "<value>"
      }
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More developer servers

All 6,250 →
ServerRunsEndpoint or package
Kadam Ad NetworkKadam advertising platform — manage ads, campaigns, creatives, audiences and stats.Local · stdionpm: @kadam-net/mcp-server
Kadent ScanFree, read-only security scanner for remote MCP servers, before you connect them.Remote · HTTPmcp.kadent.so
Kael MCP Server16 AI-native tools with dual SSE + streamable-http transport. Free tier available.Remote · SSE, HTTPkael.ink
Kafka Dataops MCPDataOps Kafka MCP server with consumer lag diagnosis and broker monitoring.Local · stdioPyPI: kafka-dataops-mcp
KagamiDeterministic prompt-injection detector; signed, offline-verifiable verdicts. Not an LLM.Remote · HTTPkagami.obolpay.xyz
KageVerified memory for coding agents: claims cited against code, stale withheld, savings receipts.Local · stdionpm: @kage-core/kage-graph-mcp
Kagura Memory CloudPersistent memory for AI assistants: store, search, and connect knowledge across conversations.Remote · HTTPmemory.kagura-ai.com
KāheaDeterministic HTTP/WebSocket testing and policy-gated API execution for AI agents.Local · stdioMCP Bundle (.mcpb): copyleftdev/kahea/releases/download/v0.3.1/kahea